English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Ground Penetrating Radar (GPR) has been widely used to estimate the healthyoperation of some urban roads and underground facilities. When identifyingsubsurface anomalies by GPR in an area, the obtained data could be unbalanced,and the numbers and types of possible underground anomalies could not beacknowledged in advance. In this paper, a novel method is proposed to improvethe subsurface anomaly detection from GPR B-scan images. A normal (i.e. withoutsubsurface objects) GPR image section is firstly collected in the detectedarea. Concerning that the GPR image is essentially the representation ofelectromagnetic (EM) wave and propagation time, and to preserve both thesubsurface background and objects' details, the normal GPR image is segmentedand then fused with simulated GPR images that contain different kinds ofobjects to generate the synthetic data for the detection area based on thewavelet decompositions. Pre-trained CNNs could then be fine-tuned with thesynthetic data, and utilized to extract features of segmented GPR imagessubsequently obtained in the detection area. The extracted features could beclassified by the one-class learning algorithm in the feature space withoutpre-set anomaly types or numbers. The conducted experiments demonstrate thatfine-tuning the pre-trained CNN with the proposed synthetic data couldeffectively improve the feature extraction of the network for the objects inthe detection area. Besides, the proposed method requires only a section ofnormal data that could be easily obtained in the detection area, and could alsomeet the timeliness requirements in practical applications.

Improving the Anomaly Detection in GPR Images by Fine-Tuning CNNs with Synthetic Data